RANGER: Sparsely-Gated Mixture-of-Experts with Adaptive Retrieval Re-ranking for Pathology Report Generation
On the map: Mixture-of-experts → Medical and biomedical MoE
Abstract (arXiv)
Pathology report generation remains a relatively under-explored downstream task, primarily due to the gigapixel scale and complex morphological heterogeneity of Whole Slide Images (WSIs). Existing pathology report generation frameworks typically employ transformer architectures, relying on a homogeneous decoder architecture and static knowledge retrieval integration. Such architectures limit generative specialization and may introduce noisy external guidance during the report generation process. To address these limitations, we propose RANGER, a sparsely-gated Mixture-of-Experts (MoE) framework with adaptive retrieval re-ranking for pathology report generation. Specifically, we integrate a sparsely gated MoE into the decoder, along with noisy top-k routing and load-balancing regularization, to enable dynamic expert specialization across various diagnostic patterns. Additionally, we introduce an adaptive retrieval re-ranking module that selectively refines retrieved memory from a knowledge base before integration, reducing noise and improving semantic alignment based on visual feature representations. We perform extensive experiments on the PathText-BRCA dataset and demonstrate consistent improvements over existing approaches across standard natural language generation metrics. Our full RANGER model achieves optimal performance on PathText dataset, reaching BLEU-1 to BLEU-4 scores of 0.4598, 0.3044, 0.2036, and 0.1435, respectively, with METEOR of 0.1883, and ROUGE-L of 0.3038, validating the effectiveness of dynamic expert routing and adaptive knowledge refinement for semantically grounded pathology report generation.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Medical and biomedical MoE, one of 12 directions in Mixture-of-experts. Builds on 26 of its 32 references that are in the map. First posted on arXiv 4 Mar 2026.
Builds on
26 of 32 references.
References · 26
- 2017Attention Is All You Needcited by 59,932
- 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
- 2021GLaM: Efficient Scaling of Language Models with Mixture-of-Expertscited by 890
- 2014Show and Tell: A Neural Image Caption Generatorcited by 877
- 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 738
- 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 549
- 2022ST-MoE: Designing Stable and Transferable Sparse Expert Modelscited by 391
- 2020Generating Radiology Reports via Memory-driven Transformercited by 363
- 2024OpenMoE: An Early Effort on Open Mixture-of-Experts Language Modelscited by 185
- 2022Cross-modal Memory Networks for Radiology Report Generationcited by 183
- 2021DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learningcited by 114
- 2023Soft Merging of Experts with Adaptive Routingcited by 88
14 more
- 2023Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videoscited by 84
- 2024HistGen: Histopathology Report Generation via Local-Global Feature Encoding and Cross-modal Context Interactioncited by 43
- 2024AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Modelscited by 41
- 2024Lory: Fully Differentiable Mixture-of-Experts for Autoregressive Language Model Pre-trainingcited by 37
- 2023WsiCaption: Multiple Instance Generation of Pathology Reports for Gigapixel Whole-Slide Imagescited by 31
- 2025Evidence-based diagnostic reasoning with multi-agent copilot for human pathologycited by 26
- 2025Activating Associative Disease-Aware Vision Token Memory for LLM-Based X-ray Report Generationcited by 11
- 2023Automatic Report Generation for Histopathology images using pre-trained Vision Transformerscited by 9
- 2025Historical Report Guided Bi-modal Concurrent Learning for Pathology Report Generationcited by 7
- 2025Pathology Report Generation and Multimodal Representation Learning for Cutaneous Melanocytic Lesionscited by 6
- 2025PolyPath: Adapting a Large Multimodal Model for Multi-slide Pathology Report Generationcited by 4
- 2025LLM-driven Medical Report Generation via Communication-efficient Heterogeneous Federated Learningcited by 4
- 2025S2D-ALIGN: Shallow-to-Deep Auxiliary Learning for Anatomically-Grounded Radiology Report Generationcited by 4
- 2026HistoMet: A Pan-Cancer Deep Learning Framework for Prognostic Prediction of Metastatic Progression and Site Tropism from Primary Tumor Histopathologycited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2026Benchmarking Vision-Language Models for Automated Pathology Diagnosis and Report Generation
- 2026Decomposing Whole Slide Image Report Generation with Graph-Constrained Multiple Instance Learning Workflows
- 2026Footprint-Guided Exemplar-Free Continual Histopathology Report Generation
- 2026Simple Token-Efficient Vision-Language Model for Case-level Pathology Synoptic Report Generation
- 2025YpathRAG:A Retrieval-Augmented Generation Framework and Benchmark for Pathology
- 2025MPath: Multimodal Pathology Report Generation from Whole Slide Images
- 2024PathAlign: A vision-language model for whole slide images in histopathology
- 2025Histopathology Image Report Generation by Vision Language Model with Multimodal In-Context Learning